检索结果-内蒙古大学图书馆

2D Polynomial Regression Modeling for Predictive Analysis of Glucose Concentration in NP-Model Fractal Microwave Sensor Using Frequency and Transmission Coefficient Disparities

2D Polynomial Regression Modeling for Predictive Analysis of...

引用

13th International Electrical engineering Congress, iEECON 2025

作者： Nantapanich, Nutyada Mahatthanajatuphat, Pisit Wongsin, Norakamon Lee, Wilaiporn Rajamangala University of Technology Thanyaburi Faculty of Engineering Department of Electronics and Telecommunication Engineering Pathum Thani Thailand Yothinburana School Regular Program in Mathematics-Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand

ISBN: (纸本)9798331543952

The article introduces a two-dimensional polynomial regression model for the predictive analysis of glucose concentration in a fractal microwave sensor NP model, utilizing frequency and transmission coefficient differences to examine their correlation with glucose concentration levels. The sensor employed in this investigation is fabricated on an economical FR-4 substrate to minimize costs. The sensor structure is developed with the fractal structure reduction method established by the NP model to operate at a frequency of roughly 2.97 GHz. The CST Studio software is utilized to analyze the findings from the simulation of the suggested sensor structure. Furthermore, the proposed sensor is integrated into a test apparatus comprising a sensor platform and a liquid tube constructed from PPA material. The liquid under examination is a glucose and water mixture at varying concentrations. It was analyzed using a VNA instrument to evaluate its frequency response and the magnitude of the alteration in the transmission coefficient. The values are utilized to create a two-dimensional polynomial regression model. The experiments demonstrated that the proposed sensor model possesses an Adjusted R² value of 0.99499 and an average error of approximately 3.57% for glucose concentration analysis throughout the range of 5% to 30%, with sensitivities of 0.00879 dB/% for insertion loss and 0.092 MHz/% for frequency variation, facilitating accurate glucose concentration prediction analysis. © 2025 IEEE.

关键词： Polynomial regression

来源：评论

学校读者我要写书评

暂无评论

Air Particulate Matters Auto-Rule-Based Labeling to Support Long-Distance Run Environment Data Classification 13

Air Particulate Matters Auto-Rule-Based Labeling to Support ...

引用

13th IEEE Symposium on computer Applications and Industrial Electronics, ISCAIE 2023

作者： Wandy, Wandy Adi, Kusworo Ayu, Media Anugerah Diponegoro University Doctoral Program of Information Systems School of Postgraduate Studies Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Physics Semarang Indonesia Sampoerna University Faculty of Engineering and Technology Department of Computer Science South Jakarta Indonesia

ISBN: (纸本)9798350347319

Sports Science is an interdisciplinary and multidisciplinary science that strives to increase athletic performance and endurance. Sport Science recognizes and prevents injuries. Sensors and statistics formalize Sports Science. Runners need coaches and teams to support them before, during, and after the run race. Coaches generate running training plans to boost performance. Running race performances may be impacted by air pollution exposure while training, so coaches should consider limiting air pollution exposure when training. One of the external factors is Particulate Matter (PM2.5 and PM10). Sensors connecting to the Internet can record external factors and produce csv data. The foundation of supervised machine learning is the labeling process. Labeling a set of data is one of the laborious and time-consuming phases in every machine-learning application because it requires verifying the accuracy of the labels and making any necessary revisions. This research aimed to find a solution to automatically label numerous air particulate matter raw data using a rule based on parameters to reduce manual work, human errors and faster processes. This labeled data will later be used for supervised machine learning classification to support the coach in generating training programs for the runners in a Sports Information System. Based on Indonesia Air Quality index rule-based approach, labeled text data in csv has been generated and tested with PM2.5 and PM10 parameters in three scenarios with a 100% success rate. It was possible to automate the labeling process, and it explained how automation results in fast and accurate results. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

2D Polynomial Regression Modeling for Predictive Analysis of Glucose Concentration in NP-Model Fractal Microwave Sensor Using Frequency and Transmission Coefficient Disparities

2D Polynomial Regression Modeling for Predictive Analysis of...

引用

International Electrical engineering Congress (iEECON)

作者： Nutyada Nantapanich Pisit Mahatthanajatuphat Norakamon Wongsin Wilaiporn Lee Department of Electronics and Telecommunication Engineering Faculty of Engineering Rajamangala University of Technology Thanyaburi Pathum Thani Thailand Regular Program in Mathematics-Science Yothinburana School Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

关键词： Analytical models Adaptation models Correlation Liquids Predictive models Microwave sensors Polynomials Fractals Glucose Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence: A Promising Prospect for Better Management of Diabetic Patients 5

Artificial Intelligence: A Promising Prospect for Better Man...

引用

5th IEEE International Conference on Artificial Intelligence and Big Data, ICAIBD 2022

作者： Hossin, Md Altab Islam, Md Safiqul Hassan, Sani Abubakar Ukwuoma, Chiagoziem Chima Nuri, Most. Miftahul Jannat Siddiquee, Md. Tofael Alam Chengdu University School of Innovation and Entrepreneurship Chengdu China Thakurgaon Polytechnic Institute Department of Computer Technology Thakurgaon Bangladesh University of Electronic Science and Technology of China School of Electronics Science and Engineering Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Hajee Mohammad Danesh Science and Technology University Department of Electronic and Communication Engineering Dinajpur Bangladesh Mymensingh Polytechnic Institute Department of Computer Science and Engineering Mymensingh Bangladesh

ISBN: (纸本)9781665499132

Diabetic as an incurable chronic disease is increasing rapidly over time, and its impacts on other diseases are also striking. Indeed, science and technology have drastically developed, and it is also in the healthcare section. Getting diabetes education to help self-management is essential to help patients enhance their metabolic control and quality of life. Using artificial intelligence (AI) technologies, we can make significant progress in transforming available genetic data and clinical information into valuable knowledge. In disease education, given its potential benefits in encouraging individualization and full-course education intervention, AI would be extremely advantageous based on the unique situations of different individuals. The use of AI in different facets of diabetes education was explored based on collected data. © 2022 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Thermal energy dependent transient permittivity of epsilon-near-zero material

引用

Science China(Physics,Mechanics & Astronomy) 2022年第8期65卷 96-101页

作者： Heng Wang Lixun Sun Kang Du Wending Zhang SooJin Chua Guixin Li Ting Mei MOE Key Laboratory of Material Physics and Chemistry under Extraordinary Conditions and Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi’an710129China Department of Materials Science and Engineering Southern University of Science and TechnologyShenzhen518055China Shenzhen Institute for Quantum Science and Engineering Southern University of Science and TechnologyShenzhen518055China Department of Electrical and Computer Engineering National University of SingaporeSingapore117583Singapore LEES Program Singapore-MIT Alliance for Research&Technology(SMART)Singapore138602Singapore

Transparent conductive oxides exhibit attractive optical nonlinearity with ultrafast response and giant refractive index change near the epsilon-near-zero(ENZ) wavelength, originating from the intraband dynamics of conduction electrons. The optical nonlinearity of ENZ materials has been explained by using the overall-effective-mass and the overall-scattering-time of electrons in the extended Drude model. However, their response to optical excitation is yet the last building block to complete the theory. In this paper, the concept of thermal energy is theoretically proposed to account for the total energy of conduction electrons exceeding their thermal equilibrium value. The time-varying thermal energy is adopted to describe the transient optical response of indium-tin-oxide(ITO), a typical ENZ material. A spectrally-resolved femtosecond pump-probe experiment was conducted to verify our theory. By correlating the thermal energy with the pumping density, both the giant change and the transient response of the permittivity of ITO can be predicted. The results in this work provide a new methodology to describe the transient permittivities of ENZ materials, which will benefit the design of ENZ-based nonlinear photonic devices.

关键词： epsilon-near-zero optical nonlinearity transient response thermal energy hot electron indium tin oxide

来源：评论

学校读者我要写书评

暂无评论

FedPylot: Navigating Federated Learning for Real-Time Object Detection in Internet of Vehicles

arXiv

引用

arXiv 2024年

作者： Quéméneur, Cyprien Cherkaoui, Soumaya The Department of Computer and Software Engineering Polytechnique Montréal MontrealQCH3T 1J4 Canada

The Internet of Vehicles (IoV) emerges as a pivotal component for autonomous driving and intelligent transportation systems (ITS), by enabling low-latency big data processing in a dense interconnected network that comprises vehicles, infrastructures, pedestrians and the cloud. Autonomous vehicles are heavily reliant on machine learning (ML) and can strongly benefit from the wealth of sensory data generated at the edge, which calls for measures to reconcile model training with preserving the privacy of sensitive user data. Federated learning (FL) stands out as a promising solution to train sophisticated ML models in vehicular networks while protecting the privacy of road users and mitigating communication overhead. This paper examines the federated optimization of the cutting-edge YOLOv7 model to tackle real-time object detection amid data heterogeneity, encompassing unbalancedness, concept drift, and label distribution skews. To this end, we introduce FedPylot, a lightweight MPI-based prototype to simulate federated object detection experiments on high-performance computing (HPC) systems, where we safeguard server-client communications using hybrid encryption. Our study factors in accuracy, communication cost, and inference speed, thereby presenting a balanced approach to the challenges faced by autonomous vehicles. We demonstrate promising results for the applicability of FL in IoV and hope that FedPylot will provide a basis for future research into federated real-time object detection. The source code is available at https://***/cyprienquemeneur/fedpylot. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

DeepJDOT: Deep joint distribution optimal transport in facial recognition

DeepJDOT: Deep joint distribution optimal transport in facia...

引用

作者： Yuchen Cai Chenglong Wen Haoyuan Chen Yijia Liu Haofei Peng Computer Science and Software Engineer Department Rose-Hulman Institute of Technology Department of Physics University of Toronto Department of Physics University of Washington Department of Water Conservancy and Civil Engineering China Agricultural University Department of Information Engineering Xi'an Jiaotong University

This paper explores the application of deep learning in domain adaptation, with a particular focus on using the Deep Joint Distribution Optimal Transportation(DeepJDOT)method for face recognition. We test DeepJDOT on a series of visual domain adaptation tasks and find that it exhibits high accuracy and competitive advantage, especially under smaller image sizes, compared to recent state-of-the-art competitors. This research not only highlights the potential of deep learning in domain adaptation but also underscores DeepJDOT as an effective approach for improving the performance of applications like face ***, we introduce a domain adaptation-tailored loss function based on optimal transport to further enhance model performance. This study provides valuable insights and methods for research in visual domain adaptation and face recognition.

关键词： DeepJDOT Convolutional Neural Network computer vision

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Dynamic Asynchronous Federated Learning in Mobile Edge Computing Networks

Energy-Efficient Dynamic Asynchronous Federated Learning in ...

引用

IEEE International Conference on Communications (ICC)

作者： Guozeng Xu Xiuhua Li Hui Li Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

To break data silos and address the challenge of green communication, federated learning (FL) is widely used at network edges to train deep learning models in mobile edge computing (MEC) networks. However, many existing FL algorithms do not fully consider the dynamic environment, resulting in slower convergence of the model and larger training energy consumption. In this paper, we design a dynamic asynchronous federated learning (DAFL) model to improve the efficiency of FL in MEC networks. Specifically, we dynamically choose a certain number of mobile devices (MDs) by their arrival order to participate in the global aggregation at each epoch. Meanwhile, we analyze the energy consumption model of local update and upload update, and formulate the problem as a dynamic sequential decision problem to minimize the energy consumption, which is NP-hard. To address it, we propose an energy-efficient algorithm based on deep reinforcement learning named DDAFL, to intelligently determine the number of MDs participating in global aggregation according to the state of MEC networks at each epoch. Compared with baseline schemes, the proposed algorithm can significantly reduce energy consumption and accelerate model convergence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Queue Management Priority-Based Traffic engineering Method 9

Queue Management Priority-Based Traffic Engineering Method

引用

9th IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2022

作者： Lemeshko, Oleksandr Yeremenko, Oleksandra Persikov, Anatoliy Yevdokymenko, Maryna Mersni, Amal Harkusha, Serhii Kharkiv National University of Radio Electronics V.V. Popovskyy Department of Infocommunication Engineering Kharkiv Ukraine International University of Sarajevo Department of Engineering Computer Sciences and Engineering Program Sarajevo Bosnia and Herzegovina Poltava University of Economics and Trade Department of Document Studies and Information Activities in Economic Systems Poltava Ukraine

ISBN: (纸本)9798350398915

The work proposes the improvement of queue management priority-based Traffic engineering method. It is based on the interaction prediction principle to coordinate decisions at various levels. The lower level of calculations is responsible, firstly, for the distribution and aggregation of packet flows between the macro queues and sub-queues organized on the router interface (congestion management task), and, secondly, for the balanced distribution of interface bandwidth among sub-queues, weighted relative to their priorities (resource allocation task). The upper level of the method's calculations is accountable for distributing the interface's bandwidth between macro queues by performing the iterative procedure. The numerical research results of the proposed two-level queue management method confirmed its effectiveness in ensuring high scalability, balanced priority- based distribution of packet flows and interface bandwidth between the macro queues and sub-queues organized on it. The method demonstrated high coordination procedure convergence and the final quality of centralized calculations. © 2022 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Exploring Loss Landscapes through the Lens of Spin Glass Theory

arXiv

引用

arXiv 2024年

作者： Liao, Hao Zhang, Wei Huang, Zhanyi Long, Zexiao Zhou, Mingyang Wu, Xiaoqun Mao, Rui Yeung, Chi Ho College of Computer Science and Software Engineering Shenzhen University China Department of Science and Environmental Studies The Education University of Hong Kong Hong Kong

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized space, remains limited. For instance, in deep neural networks (DNNs), their internal representations, decision-making mechanism, absence of overfitting in an over-parametrized space, superior generalizability, etc., remain less understood. Successful applications are often considered as empirical rather than scientific achievement. This paper delves into the loss landscape of DNNs through the lens of spin glass in statistical physics, a system characterized by a complex energy landscape with numerous metastable states, as a novel perspective in understanding how DNNs work. We investigated the loss landscape of single hidden layer neural networks activated by Rectified Linear Unit (ReLU) function, and introduced several protocols to examine the analogy between DNNs and spin glass. Specifically, we used (1) random walk in the parameter space of DNNs to unravel the structures in their loss landscape;(2) a permutation-interpolation protocol to study the connection between copies of identical regions in the loss landscape due to the permutation symmetry in the hidden layers;(3) hierarchical clustering to reveal the hierarchy among trained solutions of DNNs, reminiscent of the so-called Replica Symmetry Breaking (RSB) phenomenon (i.e. the Parisi solution) in spin glass;(4) finally, we examine the relationship between the ruggedness of DNN’s loss landscape and its generalizability, showing an improvement of flattened minima. © 2024, CC BY-NC-ND.

关键词： Spin glass

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：